Write a Blog >>
PLDI 2020
Mon 15 - Fri 19 June 2020

Several programming languages use garbage collectors (GCs) to automatically manage memory for the programmer. Such collectors must decide when to look for unreachable objects to free, which can have a large performance impact on some applications. In this preliminary work, we propose a design for a learned garbage collector that autonomously learns over time when to perform collections. By using reinforcement learning, our design can incorporate user-defined reward functions, allowing an autonomous garbage collector to learn to optimize the exact metric the user desires (e.g., request latency or queries per second). We conduct an initial experimental study on a prototype, demonstrating that an approach based on tabular Q learning may be promising.

Tue 16 Jun
Times are displayed in time zone: (GMT-07:00) Pacific Time (US & Canada) change

mapl-2020-papers
14:00 - 15:00: MAPL - Formal Methods and Reinforcement Learning at MAPL live stream
Chair(s): Aws AlbarghouthiUniversity of Wisconsin-Madison, USA
mapl-2020-papers14:00 - 14:30
Talk
Lujing CenMIT CSAIL, Ryan MarcusMIT CSAIL / Intel Labs, Hongzi MaoMIT CSAIL, Justin GottschlichIntel Labs / Penn, Mohammad AlizadehMIT CSAIL, Tim KraskaMIT CSAIL
mapl-2020-papers14:30 - 15:00
Talk
Swarat ChaudhuriRice University